INDEX

Explanations

phrases related to historical transactions

oai_token-act-pair · gemini-2.0-flash

say "doesn/does"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DoubleQuotes

-0.79

IsContent

-0.57

RegistryLite

-0.56

tvguidetime

-0.54

spesies

-0.54

makeText

-0.54

aarrggbb

-0.53

ngrx

-0.53

asteroide

-0.53

PerformLayout

-0.53

POSITIVE LOGITS

 doesn

1.73

doesn

1.51

 does

1.48

 Doesn

1.47

Doesn

1.39

 doesnt

1.34

does

1.30

Does

1.25

 Does

1.20

 didn

1.16

Activations Density 1.868%

phrases related to historical transactions

say "doesn/does"

No Comments

No Known Activations